cxcscmu/SkillLearnBench - 13ページ

run2-pdf-calendar-parsing

Precisely parse a PDF day-view calendar to extract event times, durations, and colors by reading visual block positions and the 15-minute grid.

原文の言語: 英語

run2-timezone-dst

Convert US time zones to the calendar's local timezone, correctly handling Daylight Saving Time for dates in March through November.

原文の言語: 英語

run2-d3-bubble-chart

Creating D3.js v6 bubble charts with market cap sizing (scaleSqrt), sector coloring, inside ticker labels, and ETF uniform sizing — with correct tooltip suppression for ETFs.

原文の言語: 英語

run2-d3-force-cluster

D3.js v6 force simulation for clustered bubbles by category using forceX/forceY anchors, forceCollide for no overlap, with truly deterministic initial positions.

原文の言語: 英語

run2-d3-interactive-table

Building a scrollable D3.js HTML table linked to a bubble chart with bidirectional click-highlight, correct scrollIntoView for overflow containers, and sector color badges.

原文の言語: 英語

run2-glm-calibration

How to run and calibrate GLM3 for lake temperature simulation - includes correct parameter effects, grid search strategy, and verified working parameter ranges.

原文の言語: 英語

run2-glm-netcdf-analysis

How to read GLM3 NetCDF output (shape/dimension details verified) and extract simulated temperature profiles matched to field observations.

原文の言語: 英語

run2-glm-rmse-metrics

Exact RMSE metric computation for GLM lake temperature evaluation - verified matching procedure with correct threshold values.

原文の言語: 英語

run2-itinerary-data-exploration

Explore and query travel dataset files (CSV/TXT) to find cities, restaurants, accommodations, attractions, and driving distances — with precise filtering patterns and data field notes.

原文の言語: 英語

run2-itinerary-planning

Build a multi-city road-trip travel itinerary from dataset files with complete budget tracking, pet-friendly constraints, cuisine coverage, and correct JSON output format.

原文の言語: 英語

run2-ffmpeg-keyframes

Extract I-frame keyframes from video files using FFmpeg CLI, saving as zero-padded PNG sequences starting at 001.

原文の言語: 英語

run2-image-grayscale

Convert PNG images to grayscale inplace using ImageMagick; covers both keyframes and template images for consistent matching.

原文の言語: 英語

run2-object-counting

Count template objects in keyframes using count_objects.py; parse integer from output string and generate a CSV with results per frame.

原文の言語: 英語

run2-excel-index-match

Use INDEX&MATCH with two conditions (series code + year) to populate data tables in Excel from a source sheet, with proper anchoring for copyable formulas.

原文の言語: 英語

run2-excel-sumproduct

Calculate GDP-weighted mean of net exports as % of GDP using SUMPRODUCT in Excel, including all supporting statistics (min, max, median, percentiles).

原文の言語: 英語

run2-openpyxl-editing

Safely insert Excel formulas into specific cells using openpyxl without altering formatting, colors, or structure of existing workbooks.

原文の言語: 英語

run2-design-standards

Refined skill for enforcing Anthropic corporate brand identity with precise HEX token usage.

原文の言語: 英語

run2-image-generation

Enhanced skill for programmatic design, incorporating system-level dependency management for image generation libraries.

原文の言語: 英語

run2-modern-chinese-poetry

Provides guidelines on modern Mandarin pronunciation and rhyming for classical forms.

原文の言語: 英語

run2-poetic-mastery

Advanced guidance for writing regulated verse, covering parallelism, rhythm, and emotional depth.

原文の言語: 英語

run2-pdf-form-filler

Improved skill for filling XFA/non-standard PDFs using FreeText annotations when field mapping is unavailable.

原文の言語: 英語

run2-dbscan-custom-metric

Implementation of DBSCAN with custom weighted Euclidean metric, optimized for parallel execution.

原文の言語: 英語

run2-matching-evaluation

Efficient greedy matching of cluster centroids to expert points with distance constraint.

原文の言語: 英語

run2-pareto-optimization

Identifying the Pareto frontier for a set of results, efficient implementation.

原文の言語: 英語

run2-csv-generation

Robust JSON-to-CSV parser for Trivy vulnerability reports.

原文の言語: 英語

run2-trivy-audit

Run Trivy in offline mode to identify high and critical vulnerabilities in package-lock.json with specific flag usage.

原文の言語: 英語

run2-geospatial-analysis

Geospatial data analysis with geopandas for distance calculations, filtering, and modern API usage.

原文の言語: 英語

run2-file-navigation

Efficient recursive exploration and content searching across large datasets.

原文の言語: 英語

run2-json-processing

Provides advanced techniques for reading, parsing, and structured writing of JSON data, including complex filtering and aggregation.

原文の言語: 英語

run2-13f-analysis

Improved 13F dataset analysis functions (includes better handling of TSVs).

原文の言語: 英語

run2-druid-patching

Improved skill for creating and applying robust patches to the Druid source code, including verification steps.

原文の言語: 英語

run2-maven-build

Improved skill for building Apache Druid with Maven, focusing on skipping non-essential tasks efficiently.

原文の言語: 英語

run2-github-analytics

Advanced skills for fetching, filtering, and aggregating GitHub data using `gh` CLI and `jq`.

原文の言語: 英語

run2-pytorch-tensor-ops

Robust PyTorch tensor operations for implementing loss functions, including handling device placement and numerical stability.

原文の言語: 英語

run2-simpo-implementation

Detailed SimPO implementation logic covering reward formulation and margin-based loss computation.

原文の言語: 英語

run2-docx-processing

A robust skill for template processing in DOCX files, handling placeholders and complex conditional blocks spanning multiple paragraphs.

原文の言語: 英語

file-analyzer

Robust extraction of text from various file formats (PDF, DOCX, etc).

原文の言語: 英語

subject-classifier

Maps extracted text to one of the 5 defined subjects.

原文の言語: 英語

run2-scala-data-abstractions

Idiomatic data modeling with case classes, sealed traits, and exhaustive matching.

原文の言語: 英語

run2-scala-json-handling

Idiomatic JSON handling using Circe.

原文の言語: 英語